© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 117610
    Prev
    Next
    INDEX
    Explanations

    words indicating capability or ability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    steam
    -0.07
    abra
    -0.06
    edl
    -0.06
    DECL
    -0.06
    inea
    -0.06
    ALLED
    -0.06
    orsi
    -0.06
    ienes
    -0.06
    acters
    -0.06
    HITE
    -0.06
    POSITIVE LOGITS
    ãn
    0.06
    ÌĨ
    0.06
    #
    0.06
    ë¡
    0.06
     Bram
    0.06
    avn
    0.06
     -,
    0.06
     behaviors
    0.06
     Modeling
    0.06
    theless
    0.06
    Activations Density 0.000%

    No Known Activations